How to Use the Apify MCP in LlamaIndex

Q: How do I index Apify dataset items using LlamaIndex?

Use getdatasetresults to retrieve the scraped items as JSON. Convert these items into LlamaIndex Node objects, then insert them directly into your vector store index.

Q: How does the Apify MCP Server integrate with LlamaIndex storage?

The server acts as a live data source. It uses tools like listdatasets to let your agent find and pull data from Apify storage directly into your vector database.

Index live web data from Apify directly into your LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apify MCP to LlamaIndex

Create your Vinkius account to connect Apify to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Apify with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Apify Datasets into LlamaIndex Nodes

Use `get_dataset_results` via this MCP tool to pull raw web data right into your LlamaIndex ingestion pipeline. The tool fetches structured JSON from your scraper runs, which your pipeline converts into LlamaIndex text nodes. Instead of dealing with messy raw HTML, your query engine uses `list_datasets` to find the right run. This lets you build RAG systems that search through freshly scraped web pages rather than stale offline archives.

On-Demand Ingestion with this MCP Server

When your LlamaIndex router engine encounters a query about a topic it lacks, it triggers `run_actor` to scrape the web. It monitors the progress using `get_run_details` before indexing the new findings on the fly. This creates a self-updating LlamaIndex vector store. The agent decides when its local index is too old, runs the scraper, and updates its document store without human intervention.

Map Scrapers to LlamaIndex Query Engines

Your LlamaIndex agent uses `list_actors` to inspect your available scraping tools. It matches the user's query intent against your scrapers to decide which actor is best suited for the index retrieval task. By combining this with `list_actor_tasks`, the query engine maps pre-configured scraping parameters directly to the run. You get structured, predictable web data mapped straight to your LlamaIndex indices.

Setup guide

Set up Apify MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Apify MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Apify tools.",
)
response = await agent.run("List recent Apify data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Apify. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Apify now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Apify MCP in LlamaIndex

Use `get_dataset_results` to retrieve the scraped items as JSON. Convert these items into LlamaIndex Node objects, then insert them directly into your vector store index.

Yes. If a query finds no relevant nodes, your agent can call `run_actor` to scrape the missing data. It waits for the run to finish, indexes the new data, and answers the query.

The server acts as a live data source. It uses tools like `list_datasets` to let your agent find and pull data from Apify storage directly into your vector database.

No. You can use any actor from the Apify Store. Your agent runs them via `run_actor` and fetches the structured results using the server tools.

Vinkius runs the MCP connection in a zero-trust, ephemeral sandbox. Your scraped web data and dataset tokens are passed directly to your LlamaIndex instance without being logged or stored on our servers.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript